Pytorch framework learning record 7 - convolutional layer

Pytorch框架学习记录7——卷积层

1. torch.nn.Conv2d 介绍

torch.nn.Conv2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, padding_mode=‘zeros’, device=None, dtype=None)

参数

• in_channels ( int ) – 输入图像中的通道数
• out_channels ( int ) – 卷积产生的通道数
• kernel_size ( intortuple ) – 卷积核的大小
• stride ( intortuple,optional ) – 卷积的步幅.默认值：1
• padding ( int,tuple或str,optional ) – 添加到输入的所有四个边的填充.默认值：0
• padding_mode (字符串*,*可选) – 'zeros', 'reflect', 'replicate'或'circular'. 默认：'zeros'
• dilation ( intortuple,optional ) – 内核元素之间的间距.默认值：1
• groups ( int,optional ) – 从输入通道到输出通道的阻塞连接数.默认值：1
• bias ( bool,optional ) – If True,向输出添加可学习的偏差.默认：True

The formula for calculating the height and width of the input image and the height and width of the output image：
$$H_{out}=\lfloor (H_{in}+2\times padding[0]-dilation[0]\times (kernel\_size[0]-1)-1)/stride[0]+1\rfloor$$

$$W_{out}=\lfloor (W_{in}+2\times padding[1]-dilation[1]\times (kernel\_size[1]-1)-1)/stride[1]+1\rfloor$$

这里的output_channelsrepresents the number of convolution kernels,卷积核的个数=The number of output channels

2. 实例

The following example builds a simple convolutional network using the methods learned earlier,And compare the input and output images.

import torch
import torchvision.datasets
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

dataset = torchvision.datasets.CIFAR10(root='./dataset', train=False, transform=torchvision.transforms.ToTensor(),
                                       download=True)

dataloader = DataLoader(dataset=dataset, batch_size=64, num_workers=0)


class Test(nn.Module):
    def __init__(self):
        super(Test, self).__init__()
        self.conv2d = nn.Conv2d(in_channels=3, out_channels=6, kernel_size=3, stride=1, padding=0)

    def forward(self, x):
        x = self.conv2d(x)
        return x


writer = SummaryWriter("logs")
test = Test()
step = 0
for data in dataloader:
    imgs, target = data
    output = test(imgs)
    print(imgs.shape)
    print(output.shape)
    output = torch.reshape(output, (-1, 3, 30, 30))

    writer.add_images("input", imgs, step)
    writer.add_images("output", output, step)
    step += 1

原始图像：

卷积后的图像：